Mark A. Paskin
EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-01-1148
June 2001
http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/CSD-01-1148.pdf
This paper presents a probabilistic model of English grammar that is based upon "grammatical bigrams", i.e., syntactic relationships between pairs of words. Because of its simplicity, the grammatical bigram model admits cubic-time parsing and unsupervised learning algorithms, which are described in detail.
BibTeX citation:
@techreport{Paskin:CSD-01-1148, Author = {Paskin, Mark A.}, Title = {Cubic-time Parsing and Learning Algorithms for Grammatical Bigram Models}, Institution = {EECS Department, University of California, Berkeley}, Year = {2001}, Month = {Jun}, URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/5544.html}, Number = {UCB/CSD-01-1148}, Abstract = {This paper presents a probabilistic model of English grammar that is based upon "grammatical bigrams", i.e., syntactic relationships between pairs of words. Because of its simplicity, the grammatical bigram model admits cubic-time parsing and unsupervised learning algorithms, which are described in detail.} }
EndNote citation:
%0 Report %A Paskin, Mark A. %T Cubic-time Parsing and Learning Algorithms for Grammatical Bigram Models %I EECS Department, University of California, Berkeley %D 2001 %@ UCB/CSD-01-1148 %U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/5544.html %F Paskin:CSD-01-1148